paper-with-me

홈 › Papers

DOTS: Decoupling Operation and Topology in Differentiable Architecture Search

2020-10-02 · CVPR 2021 1 · Yu-Chao Gu, Li-Juan Wang, Yun Liu, Yi Yang, Yu-Huan Wu, Shao-Ping Lu, Ming-Ming Cheng

Differentiable Architecture Search (DARTS) has attracted extensive attention due to its efficiency in searching for cell structures. DARTS mainly focuses on the operation search and derives the cell topology from the operation weights. However, the operation weights can not indicate the importance of cell topology and result in poor topology rating correctness. To tackle this, we propose to Decouple the Operation and Topology Search (DOTS), which decouples the topology representation from operation weights and makes an explicit topology search. DOTS is achieved by introducing a topology search space that contains combinations of candidate edges. The proposed search space directly reflects the search objective and can be easily extended to support a flexible number of edges in the searched cell. Existing gradient-based NAS methods can be incorporated into DOTS for further improvement by the topology search. Considering that some operations (e.g., Skip-Connection) can affect the topology, we propose a group operation search scheme to preserve topology-related operations for a better topology search. The experiments on CIFAR10/100 and ImageNet demonstrate that DOTS is an effective solution for differentiable NAS.

📄 PDF Abstract BibTeX arXiv:2010.00969

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

DARTS Differentiable Architecture Search (DART) is a method for efficient architecture search. The search space is made continuous so that the architecture can be optimized with…

Similar Papers 제목 키워드 기반

Explicit Learning Topology for Differentiable Neural Architecture Search

2021-01-01 · Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu 외

Differentiable neural architecture search (NAS) has gained much success in discovering more flexible and diverse cell types. Current methods couple the operations and topology during search, and simply derive optimal topo…

Neural Architecture Search

DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation

2021-03-29 · CVPR 2021 1 · Yufan He, Dong Yang, Holger Roth, Can Zhao 외

Recently, neural architecture search (NAS) has been applied to automatically search high-performance networks for medical image segmentation. The NAS search space usually contains a network topology level (controlling co…

GPUImage SegmentationMedical Image SegmentationNeural Architecture Search+2

BARS: Joint Search of Cell Topology and Layout for Accurate and Efficient Binary ARchitectures

2020-11-21 · Tianchen Zhao, Xuefei Ning, Xiangsheng Shi, Songyi Yang 외

Binary Neural Networks (BNNs) have received significant attention due to their promising efficiency. Currently, most BNN studies directly adopt widely-used CNN architectures, which can be suboptimal for BNNs. This paper …

Neural Architecture Search

Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective

2021-12-29 · Lanning Wei, Huan Zhao, Zhiqiang He

In recent years, Graph Neural Networks (GNNs) have shown superior performance on diverse real-world applications. To improve the model capacity, besides designing aggregation operations, GNN topology design is also very …

feature selectionNeural Architecture Search

Ink Dot-Oriented Differentiable Optimization for Neural Image Halftoning

2024-01-01 · CVPR 2024 1 · Hao Jiang, Bingfeng Zhou, Yadong Mu

Halftoning is a time-honored printing technique that simulates continuous tones using ink dots (halftone dots). The resurgence of deep learning has catalyzed the emergence of innovative technologies in the printing i…